The official implementaion of SPA_CVPR2021 paper

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]

Möbius Transformation for Fast Inner Product Search on Graph

A treasure chest for visual classification and recognition powered by PaddlePaddle

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, …

😎 Finding duplicate images made easy!

Tensors and Dynamic neural networks in Python with strong GPU acceleration

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

OpenMMLab Detection Toolbox and Benchmark

[ECCV-20] Official PyTorch implementation of HoughNet, a voting-based object detector.

Object detection, 3D detection, and pose estimation using center point detection:

Deformable Convolutional Networks v2 with Pytorch

Open MMLab Detection Toolbox